← Back to community benchmarks

Qwen3.5-122B-A10B-Text-mxfp4

M4 Max (40c) · 128 GB · 4bit · 2026-04-05

Performance

64k

tokens

350.9

PP tok/s

20.3

TG tok/s

186764

TTFT (ms)

72.4

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.4

macOS macOS 15.7.5

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	469.9	53.2	62.0 GB	view
4k	539.0	51.5	63.4 GB	view
8k	533.1	46.4	64.0 GB	view
16k	503.3	33.5	65.1 GB	view
32k	446.6	30.2	67.5 GB	view
64k	350.9	20.3	72.4 GB	current
128k	238.2	0.5	82.0 GB	view